Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the word "ones" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AXB
    -0.15
    illos
    -0.15
    kyt
    -0.15
    jang
    -0.14
     Belg
    -0.14
    kol
    -0.14
    aur
    -0.14
    nda
    -0.14
    kas
    -0.14
    atura
    -0.13
    POSITIVE LOGITS
    \Bridge
    0.16
    isphere
    0.15
    QueryParam
    0.15
    ãģ£ãģį
    0.14
    -sama
    0.14
    лки
    0.14
    ovah
    0.14
    plier
    0.13
    asso
    0.13
    ahead
    0.13
    Act Density 0.008%

    No Known Activations